光谱指数助力机器学习提高玉米叶片含水量估测精度
肖娅婷 , 唐彧哲 , 王潞 , 白宇飞 , 杨海波 , 李斐
草业学报 ›› 2025, Vol. 34 ›› Issue (12) : 85 -96.
光谱指数助力机器学习提高玉米叶片含水量估测精度
Use of spectral index-assisted machine learning to improve the accuracy of maize leaf water content estimation
玉米水分状况的快速无损监测对于水分诊断和灌溉管理具有重要意义,而光谱指数是作物叶片含水量(LWC)无损实时估测的重要指标之一,然而传统的光谱指数在估测LWC时易受外界环境因素影响,导致估测精度较低。机器学习(ML)算法在预测作物水分状况方面有显著的优势,特别是针对精准农业和作物水分监测等应用。因此,本研究旨在将光谱指数与机器学习结合来进一步提高LWC的估测精度,实现玉米水分的高效利用。研究于2023-2024年在内蒙古玉米种植的典型区域进行不同水分梯度的田间试验,测定玉米叶片3个关键生育时期的高光谱反射率,分析13种水敏感的光谱指数与玉米LWC的相关关系后,利用ReliefF技术筛选主要光谱特征作为偏最小二乘(PLSR)、随机森林(RF)、高斯过程回归(GPR)3种机器学习算法的输入变量,构建玉米LWC的估测模型。结果表明,在13种水情指数中改良的DATT指数(MDATT)预测性能最佳(决定系数R2=0.52),但估测精度受生育时期和玉米叶片层位影响较大,不能有效监测玉米LWC。而将全波段光谱(350~2500 nm)和通过ReliefF技术筛选的主要光谱指数分别投入3种机器学习算法中,LWC的估测精度提升了7%~45%。其中以光谱指数作为输入特征的模型整体表现较好,RF和GPR模型在LWC估测中表现较为优越,可解释玉米LWC 88%~89%的变异。最后利用独立数据集对RF和GPR模型进行验证,RF和GPR模型决定系数R2分别为0.89和0.88,均方根误差(RMSE)为1.95%和2.04%。总体来看,光谱指数与RF和GPR算法耦合起到了级联效应,可以显著提高玉米LWC的估测精度,研究结果将为玉米LWC的估测提供可靠的方法,并为玉米水肥一体化管理提供科学有效的依据。
Rapid and non-destructive monitoring of the water status of maize (Zea mays) is important for water status diagnosis and irrigation management. Spectral indices serve as crucial tools for non-destructive real-time estimation of crop leaf water content (LWC). However, traditional spectral indices are sensitive to external environmental factors, resulting in reduced prediction accuracy when they are used to estimate LWC. Machine learning (ML) algorithms demonstrate distinct advantages in predicting crop water status, particularly when applied in precision agriculture and crop water status monitoring. Therefore the aims of this study were to enhance the accuracy of LWC estimation by integrating spectral indices with ML approaches, with an overall goal to facilitate efficient water resource utilization during maize cultivation. Field experiments with varying water gradients were conducted in typical maize cultivation regions of Inner Mongolia during 2023-2024. The hyperspectral reflectance of maize leaves were measured across three critical growth stages, and then correlation analyses were conducted between maize LWC and 13 water-sensitive spectral indices. To develop LWC estimation models, spectral features selected via the ReliefF technique were used as input variables for three ML algorithms-partial least squares regression (PLSR), random forest (RF), and Gaussian process regression (GPR). The results demonstrate that among the 13 hydrological indices, the modified DATT index exhibited optimal predictive performance (coefficient of determination R²=0.52). However, its accuracy was affected by the growth stage and leaf canopy position, limiting its effectiveness for LWC monitoring. Integrating full-spectrum data (350-2500 nm) with ReliefF-selected spectral indices into ML algorithms enhanced the accuracy of LWC estimates by 7%-45%. Models utilizing spectral indices as input features demonstrated superior overall performance, with the RF and GPR models explaining 88%-89% of LWC variability. Independent validations confirmed the robustness of the models, with coefficient of determination R² values of 0.89 (RF) and 0.88 (GPR) and root mean square error values of 1.95% and 2.04%. Our results show that the synergistic combination of spectral indices with RF/GPR algorithms had cascading effects, significantly improving the accuracy of LWC estimation. This methodology provides a reliable approach for monitoring maize water status and establishes a scientific foundation for the development of precise integrated water-fertilizer management systems.
| [1] |
Ferraretto L F, Shaver R D, Luck B D. Silage review: Recent advances and future technologies for whole-plant and fractionated corn silage harvesting. Journal of Dairy Science, 2018, 101(5): 3937-3951. |
| [2] |
Rouse Jr J W, Haas R H, Deering D W, et al. Monitoring the vernal advancement and retrogradation. TX, USA: Texas A & M University: College Station, 1974. |
| [3] |
Inoue Y, Morinaga S, Shibayama M. Non-destructive estimation of water status of intact crop leaves based on spectral reflectance measurements. Japanese Journal of Crop Science, 1993, 62(3): 462-469. |
| [4] |
Zhao S H, Wang Q, Yao Y J, et al. Estimating and validating wheat leaf water content with three MODIS spectral indexes: A case study in Ningxia Plain, China. Journal of Agricultural Science and Technology, 2016, 18(2): 387-398. |
| [5] |
Rapaport T, Hochberg U, Cochavi A, et al. The potential of the spectral ‘water balance index’(WABI) for crop irrigation scheduling. New Phytologist, 2017, 216(3): 741-757. |
| [6] |
Kunz K, Hu Y, Schmidhalter U. Carbon isotope discrimination as a key physiological trait to phenotype drought/heat resistance of future climate-resilient German winter wheat compared with relative leaf water content and canopy temperature. Frontiers in Plant Science, 2022, 13: 1043458. |
| [7] |
Zhang J, Zhang W, Xiong S, et al. Comparison of new hyperspectral index and machine learning models for prediction of winter wheat leaf water content. Plant Methods, 2021, 17(1): 1-14. |
| [8] |
Ndlovu H S, Odindi J, Sibanda M, et al. A comparative estimation of maize leaf water content using machine learning techniques and unmanned aerial vehicle (UAV)-based proximal and remotely sensed data. Remote Sensing, 2021, 13(20): 4091. |
| [9] |
Guo F, Feng Q, Yang S, et al. Estimation of potato canopy leaf water content in various growth stages using UAV hyperspectral remote sensing and machine learning. Frontiers in Plant Science, 2024, 15: 1458589. |
| [10] |
Yang C, Tan Y, Bruzzone L, et al. Discriminative feature metric learning in the affinity propagation model for band selection in hyperspectral images. Remote Sensing, 2017, 9(8): 782. |
| [11] |
Gao B C. Normalized difference water index for remote sensing of vegetation liquid water from space.//Proceedings of the Imaging spectrometry Conference. SPIE, 1995, 2480: 225-236. |
| [12] |
Peeñuuelas J, Pinol J, Ogaya R, et al. Estimation of plant water concentration by the reflectance water index WI (R900/R970). International Journal of Remote Sensing, 1997, 18(13): 2869-2875. |
| [13] |
Helskanen J. Estimating aboveground tree biomass and leaf area index in a mountain birch forest using ASTER satellite data. International Journal of Remote Sensing, 2006, 27(6): 1135-1158. |
| [14] |
Zarco-Tejada P J, Rueda C, Ustin S. Water content estimation in vegetation with MODIS reflectance data and model inversion method. Remote Sensing of Environment, 2003, 85(1): 109-124. |
| [15] |
Apan A, Held A, Phinn S, et al. Formulation and assessment of narrow-band vegetation indices from EO-1 Hyperion imagery for discriminating sugarcane disease.// Proceedings of the Spatial Sciences Institute Biennial Conference (SSC 2003): Spatial Knowledge Without Boundaries, Canberra, Australia: Spatial Sciences Institute, 2003. |
| [16] |
Gamon J, Penuelas J, Field C. A narrow-waveband spectral index that tracks diurnal changes in photosynthetic efficiency. Remote Sensing of Environment, 1992, 41(1): 35-44. |
| [17] |
Wang Z, Sun Z, Lu S. Optimal vegetation index for assessing leaf water potential using reflectance factors from the adaxial and abaxial surfaces. Computers and Electronics in Agriculture, 2020, 172: 105337. |
| [18] |
Peñuelas J, Filella I, Biel C, et al. The reflectance at the 950-970 nm region as an indicator of plant water status. International Journal of Remote Sensing, 1993, 14(10): 1887-1905. |
| [19] |
Seelig H D, Hoehn A, Stodieck L S, et al. Plant water parameters and the remote sensing R1300/R1450 leaf water index: Controlled condition dynamics during the development of water deficit stress. Irrigation Science, 2009, 27(5): 357-365. |
| [20] |
Hunt Jr E R, Daughtry C S T, Qu J J, et al. Comparison of hyperspectral retrievals with vegetation water indices for leaf and canopy water content.//Proceedings of the Remote Sensing and Modeling of Ecosystems for Sustainability Ⅷ. SPIE, 2011, 8156: 66-76. |
| [21] |
Wang L, Qu J J. NMDI: A normalized multi-band drought index for monitoring soil and vegetation moisture with satellite remote sensing. Geophysical Research Letters, 2007, 34(20): 20405. |
| [22] |
Ceccato P, Flasse S, Gregoire J M. Designing a spectral index to estimate vegetation water content from remote sensing data: Part 2. Validation and applications. Remote Sensing of Environment, 2002, 82(2/3): 198-207. |
| [23] |
Hunt Jr E R, Rock B N. Detection of changes in leaf water content using near-and middle-infrared reflectances. Remote Sensing of Environment, 1989, 30(1): 43-54. |
| [24] |
Zhang B S, Li Y Y, Chai Z. A novel random multi-subspace based ReliefF for feature selection. Knowledge-Based Systems, 2022, 252: 109400. |
| [25] |
Cheng B, Wu X. A modified PLSR method in prediction. Journal of Data Science, 2006, 4(3): 257-274. |
| [26] |
Belgiu M, Drăguţ L. Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 114: 24-31. |
| [27] |
Nguyen-Tuong D, Seeger M, Peters J. Model learning with local Gaussian process regression. Advanced Robotics, 2009, 23(15): 2015-2034. |
| [28] |
El-Hendawy S E, Al-Suhaibani N A, Elsayed S, et al. Potential of the existing and novel spectral reflectance indices for estimating the leaf water status and grain yield of spring wheat exposed to different irrigation rates. Agricultural Water Management, 2019, 217: 356-373. |
| [29] |
Wang X, Zhao C, Guo N, et al. Determining the canopy water stress for spring wheat using canopy hyperspectral reflectance data in loess plateau semiarid regions. Spectroscopy Letters, 2015, 48(7): 492-498. |
| [30] |
Wijewardana C, Alsajri F A, Irby J T, et al. Physiological assessment of water deficit in soybean using midday leaf water potential and spectral features. Journal of Plant Interactions, 2019, 14(1): 533-543. |
| [31] |
Pasqualotto N, Delegido J, Van Wittenberghe S, et al. Retrieval of canopy water content of different crop types with two new hyperspectral indices: Water absorption area index and depth water index. International Journal of Applied Earth Observation and Geoinformation, 2018, 67: 69-78. |
| [32] |
Liu X J, Chen G Q, Wang L, et al. Monitoring leaf relative water content of winter wheat based on hyperspectral index at different growth stages. Journal of Triticeae Crops, 2018, 47(7): 854-862. |
| [33] |
刘晓静, 陈国庆, 王良, 不同生育时期冬小麦叶片相对含水量高光谱监测. 麦类作物学报, 2018, 47(7): 854-862. |
| [34] |
Zhang H W, Zhang F, Zhang X L, et al. Inversion of vegetation leaf water content based on spectral index. Spectroscopy and Spectral Analysis, 2018, 38(5): 1540-1546. |
| [35] |
张海威, 张飞, 张贤龙, 光谱指数的植被叶片含水量反演. 光谱学与光谱分析, 2018, 38(5): 1540-1546. |
| [36] |
Liu R H, Zhou G S, Zhou L, et al. Remote sensing inversion of leaf and canopy water content in different growth stages of summer maize. Journal of Applied Meteorological Science, 2020, 31(1): 52-62. |
| [37] |
刘仁华, 周广胜, 周莉, 夏玉米不同生育期叶片和冠层含水量的遥感反演. 应用气象学报, 2020, 31(1): 52-62. |
| [38] |
Jin X, Xu X, Song X, et al. Estimation of leaf water content in winter wheat using grey relational analysis-partial least squares modeling with hyperspectral data. Agronomy Journal, 2013, 105(5): 1385-1392. |
| [39] |
Hasan U, Sawut M, Kasim N, et al. Hyperspectral estimation model of leaf water content in spring wheat based on grey relational analysis. Spectroscopy and Spectral Analysis, 2018, 38(12): 3905-3911. |
| [40] |
Zhang J, Tian H Q, Zhao Z Y, et al. Moisture content dectection in silage maize raw material based on hyperspectrum and improved discrete particle swarm. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(1): 285-293. |
| [41] |
张珏, 田海清, 赵志宇, 基于改进离散粒子群算法的青贮玉米原料含水率高光谱检测. 农业工程学报, 2019, 35(1): 285-293. |
| [42] |
Wang L, Zhou X, Zhu X, et al. Estimation of biomass in wheat using random forest regression algorithm and remote sensing data. The Crop Journal, 2016, 4(3): 212-219. |
国家重点研发计划(2023YFD1900404-03)
国家重点研发计划课题(2024YFD1700400)
/
| 〈 |
|
〉 |